incubator-ctakes-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Masanz, James J." <Masanz.Ja...@mayo.edu>
Subject RE: combining components
Date Fri, 19 Oct 2012 14:57:48 GMT

I have not tested all the possible combinations.

Sorry if some of this might be obvious to you, but for others' reference:
It partly depends on if you are combining aggregates or individual annotators.
You would not want to combine aggregates that would cause, for example, the tokenizer or part
of speech tagger to be run multiple times.
In addition, the clinical documents pipeline aggregate and Drug NER both create annotations
for medications, for example, so you probably would not want to use both of those aggregates
together.

If you list the ones you'd like to use together, I will try them out and see if I spot any
problems.
Also, which version of cTAKES you are using?

Regards,
James Masanz

From: ctakes-user-return-10-Masanz.James=mayo.edu@incubator.apache.org [mailto:ctakes-user-return-10-Masanz.James=mayo.edu@incubator.apache.org]
On Behalf Of Leonard Jacuzzo
Sent: Thursday, October 18, 2012 4:18 PM
To: ctakes-user@incubator.apache.org
Subject: combining components

Dear List,

I have a question about combining the functionality of cTAKES.

If I want to use the collection processing pipeline, along with DrugNER and Smoking status
etc.

Is it as simply as adding them together in the CPE gui and then using a single cas consumer
at the end.

Or do I have to run each individually?

Ideally I would like to get all of the annotations that are available in one sweep.

Any help will be greatly appreciated.

Best wishes,

Leonard

Mime
View raw message